Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.5418. Min Act: -0.1700
Data Index: 2026781 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.5106. Min Act: -0.1700
Data Index: 7188853 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1421212 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.3231. Min Act: -0.1700
Data Index: 6905763 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.2293. Min Act: -0.1700
Data Index: 3454343 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.2293. Min Act: -0.1700
Data Index: 2099464 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.2293. Min Act: -0.1700
Data Index: 3843480 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1981. Min Act: -0.1700
Data Index: 6203596 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1668. Min Act: -0.1700
Data Index: 3707053 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1981. Min Act: -0.1700
Data Index: 529861 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1668. Min Act: -0.1700
Data Index: 3269940 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1668. Min Act: -0.1700
Data Index: 4179357 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1668. Min Act: -0.1700
Data Index: 8818379 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1981. Min Act: -0.1700
Data Index: 5464278 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1043. Min Act: -0.1700
Data Index: 8210104 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1043. Min Act: -0.1700
Data Index: 6863394 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.1043. Min Act: -0.1700
Data Index: 4552000 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.0731. Min Act: -0.1700
Data Index: 4325899 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.0731. Min Act: -0.1700
Data Index: 6861669 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5418. Min Range: -5.5418
Max Act: 5.0731. Min Act: -0.1700
Data Index: 6884170 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19